Update index.html

docs/index.html

@@ -43,7 +43,7 @@ <h2>The SatisfIA project</h2>
 			in <a href="https://pik-potsdam.zoom-x.de/rec/share/nl-EAnoEGGxqvwSZvh12tovUkM784Hlo7ogDezTWCA1rvuUMUDunLdAXsp8Qy4-k.QbpcNkpL1V_aaxw_">this talk at the ENS Paris</a>.
 			There's also an earlier <a href="https://www.youtube.com/watch?v=zX0qq0K5z9c">interview on Will Petillo's Y*uTube channel</a> 
 			where Jobst talks about the rationale of non-maximizing 
-			(and also about “satisficing”, an alternative but related idea to tihis project's, see below).   
+			(and also about “satisficing”, an alternative but related idea to this project's, see below).   
 		</p>
 
             <h2>Research focus</h2>
@@ -52,9 +52,15 @@ <h2>Research focus</h2>
 		These environments are modelled as fully or partially observed <a href="https://en.wikipedia.org/wiki/Markov_decision_process">Markov Decision Processes</a>.
 		We also develop corresponding planning and/or learning algorithms, 
 		primarily variations of model-based planning and <a href="https://en.wikipedia.org/wiki/Reinforcement_learning">reinforcement learning</a>.
+		    Our <a href="http://export.arxiv.org/abs/2408.04385">first academic publication</a> is about such an algorithm.
 	    </p>
 	    <p>
-		This involves the theoretical design of agents and algorithms, implementing them in software (mostly using Python and/or <a href="https://webppl.org/">WebPPL</a>), simulating their behavior in test environments such as <a href="https://github.com/google-deepmind/ai-safety-gridworlds">AI safety gridworlds</a>, and analyzing their behavior and safety implications. The goal is to provide numerical evidence and formal proofs where possible, and to contribute to the academic and non-academic discourse through publications and <a href="https://www.lesswrong.com/s/4TT69Yt5FDWijAWab">explanatory blog posts</a>.
+		This involves the theoretical design of agents and algorithms, implementing them in software (mostly using Python and/or <a href="https://webppl.org/">WebPPL</a>), 
+		    simulating their behavior in test environments such as <a href="https://github.com/google-deepmind/ai-safety-gridworlds">AI safety gridworlds</a>, 
+		    and analyzing their behavior and safety implications. 
+		    The goal is to provide numerical evidence and formal proofs where possible, and to contribute to the academic and non-academic discourse through publications 
+		    such as <a href="http://export.arxiv.org/abs/2408.04385">this theory paper</a>
+		    and a <a href="https://www.lesswrong.com/s/4TT69Yt5FDWijAWab">sequence of blog posts</a>.
             </p>
             <h2>Motivation and background</h2>
             <p>